llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score

64 vs 48

Hardware Fit

56 vs 53

Quality Score

70 vs 45

Hardware

llama3.1:8b qwen3:4b

MachineMac Mini—

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modeunknownunknown

Performance

llama3.1:8b qwen3:4b

Tokens/sec5.511.3

TTFT1.4 s9.2 s

Load time3.7 s0.1 s

Memory usage28.6 GB7.2 GB

Memory %45%23%

HW Fit Score Breakdown

llama3.1:8b

Speed

5/40

TTFT

22/30

Memory

29/30

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

Quality

llama3.1:8b

Reasoning

12/20

Coding

17/20

Instruction

14/20

Structured

13/15

Math

4/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

View llama3.1:8b details | View qwen3:4b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running